© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 47240
    Prev
    Next
    INDEX
    Explanations

    numbers like 25, 50, 125, 250, 251

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Prescott
    -0.13
     JJ
    -0.10
     Lancaster
    -0.10
     Bav
    -0.10
    iche
    -0.10
     Gavin
    -0.09
     Glenn
    -0.09
     Jeremy
    -0.09
     Jian
    -0.09
     Lana
    -0.09
    POSITIVE LOGITS
    25
    0.30
    625
    0.25
    125
    0.24
    250
    0.24
     Riley
    0.21
    025
    0.21
    251
    0.20
     ling
    0.18
    375
    0.17
     quarter
    0.16
    Activations Density 0.451%

    No Known Activations